Segmentation analysis on a multivariate time series of the foreign exchange rates

TL;DR

This paper introduces a recursive segmentation method for multivariate Gaussian mixture models to analyze foreign exchange rate time series, successfully identifying key economic periods over a decade.

Contribution

The paper proposes a novel recursive segmentation approach using Jensen-Shannon divergence for multivariate Gaussian mixtures in FX data analysis.

Findings

Identified significant economic periods in FX markets.

Demonstrated effectiveness of the segmentation method on decade-long data.

Detected multiple regime shifts related to international economic events.

Abstract

This study considers the multivariate segmentation procedure under the assumption of the multivariate Gaussian mixture. Jensen-Shannon divergence between two multivariate Gaussian distributions is employed as a discriminator and a recursive segmentation procedure is proposed. The daily log-return time series for 30 currency pairs consisting of 12 currencies for the last decade (January 3, 2001 to December 30, 2011) are analyzed using the proposed method. The proposed method can detect several important periods related to the significant affairs of the international economy.